Image Copy Detection (ICD) aims to identify manipulated content between image pairs through robust feature representation learning. While self-supervised learning (SSL) has advanced ICD systems, existing view-level contrastive methods struggle with sophisticated edits due to insufficient fine-grained correspondence learning. We address this limitation by exploiting the inherent geometric traceability in edited content through two key innovations. First, we propose PixTrace - a pixel coordinate tracking module that maintains explicit spatial mappings across editing transformations. Second, we introduce CopyNCE, a geometrically-guided contrastive loss that regularizes patch affinity using overlap ratios derived from PixTrace's verified mappings. Our method bridges pixel-level traceability with patch-level similarity learning, suppressing supervision noise in SSL training. Extensive experiments demonstrate not only state-of-the-art performance (88.7% uAP / 83.9% RP90 for matcher, 72.6% uAP / 68.4% RP90 for descriptor on DISC21 dataset) but also better interpretability over existing methods.
@article{arxiv.2602.17484,
title = {Tracing Copied Pixels and Regularizing Patch Affinity in Copy Detection},
author = {Yichen Lu and Siwei Nie and Minlong Lu and Xudong Yang and Xiaobo Zhang and Peng Zhang},
journal= {arXiv preprint arXiv:2602.17484},
year = {2026}
}
Comments
Accepted by ICCV2025 Github: https://github.com/eddielyc/CopyNCE